My name is Travis DeWolf. I am a PhD student at the University of Waterloo, Canada, in the systems design engineering department. I study computational neuroscience. More specifically, I study motor control algorithms and modelling the neural control of movement. This is a blog for things I encounter while coding and researching neuroscience, motor control, and learning.
studywolf's Latest Posts
Alright, in my last post on RL we looked at egocentric learning and what that is. We also saw that both ego and allocentric learning have their strong points, and they compliment each other. So, some combination of these two approaches seems like a good idea. In this post we’re going to look at combining […]
When an agent is learning how to move, it’s learning a set of values to associate with possible actions for each situation it encounters. We say that it’s learning the action values. When the agent learns to associate the values of taking different actions in different states, it is learning the state-action values, also referred […]
Log in to leave a comment